Initial commit

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,3 +1,162 @@
----
-license: apache-2.0
----
+---
+tags:
+  - vision
+  - dinov2
+  - hematology
+  - cytomorphology
+  - foundation-model
+license: apache-2.0
+citation: |
+  @inproceedings{koch2024dinobloom,
+    title={DinoBloom: a foundation model for generalizable cell embeddings in hematology},
+    author={Koch, Valentin and Wagner, Sophia J and Kazeminia, Salome and Sancar, Ece and Hehr, Matthias and Schnabel, Julia A and Peng, Tingying and Marr, Carsten},
+    booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
+    pages={520--530},
+    year={2024},
+    organization={Springer}
+  }
+---
+
+# DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology
+
+<div align="center">
+
+![DinoBloom](https://raw.githubusercontent.com/MarrLab/DinoBloom/main/media/logo.png)
+
+**DinoBloom** builds upon [DINOv2](https://arxiv.org/abs/2304.07193) (Meta AI) and is trained on **13 diverse publicly available datasets** of single cells from peripheral blood and bone marrow.
+
+[Paper](https://arxiv.org/abs/2404.05022) | [GitHub](https://github.com/MarrLab/DinoBloom) | [Zenodo](https://zenodo.org/records/10908163)
+
+</div>
+
+---
+
+## 🧠 Model Variants
+
+DinoBloom is available in **four sizes**:
+
+| Model | Feature Dim | Parameters | Checkpoint |
+|-------|-------------|------------|------------|
+| **DinoBloom-S** | 384 | 22M | `pytorch_model_s.bin` |
+| **DinoBloom-B** | 768 | 86M | `pytorch_model_b.bin` |
+| **DinoBloom-L** | 1024 | 304M | `pytorch_model_l.bin` |
+| **DinoBloom-G** | 1536 | 1136M | `pytorch_model_g.bin` |
+
+---
+
+## 🚀 Usage
+
+```python
+from huggingface_hub import hf_hub_download
+import torch
+import torch.nn as nn
+
+# Choose variant: "s", "b", "l", or "g"
+variant = "b"
+
+# Configuration
+variant_config = {
+    "s": ("dinov2_vits14", 384),
+    "b": ("dinov2_vitb14", 768),
+    "l": ("dinov2_vitl14", 1024),
+    "g": ("dinov2_vitg14", 1536),
+}
+
+dinov2_model, embed_dim = variant_config[variant]
+
+# Load base DINOv2 model
+model = torch.hub.load("facebookresearch/dinov2", dinov2_model)
+
+# Download DinoBloom weights
+ckpt_path = hf_hub_download(
+    repo_id="MarrLab/DinoBloom",
+    filename=f"pytorch_model_{variant}.bin"
+)
+ckpt = torch.load(ckpt_path, map_location="cpu")
+
+# Extract and load weights
+new_state = {
+    k.replace("backbone.", ""): v
+    for k, v in ckpt["teacher"].items()
+    if "dino_head" not in k and "ibot_head" not in k
+}
+
+num_tokens = int(1 + (224 / 14) ** 2)
+model.pos_embed = nn.Parameter(torch.zeros(1, num_tokens, embed_dim))
+model.load_state_dict(new_state, strict=True)
+model.eval()
+
+# Get transforms
+from torchvision import transforms
+transform = transforms.Compose([
+    transforms.Resize((224,224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+])
+
+# Apply to image
+from PIL import Image
+img = Image.open("path/to/cell_image")
+img_tensor = transform(img).unsqueeze(0)
+
+# Get features
+with torch.no_grad():
+    features = model(img_tensor)
+
+print(f"Features shape: {features.shape}")  # [1, 768] for DinoBloom-B
+```
+
+---
+
+## 📊 Model Performance
+
+DinoBloom outperforms existing medical and non-medical vision models in:
+
+1. **Linear probing** and **k-nearest neighbor** evaluations for cell-type classification
+2. **Weakly supervised multiple-instance learning (MIL)** for acute myeloid leukemia subtyping
+
+See our [paper](https://arxiv.org/abs/2404.05022) for detailed benchmarks.
+
+---
+
+## 🔧 Requirements
+
+```bash
+pip install torch torchvision huggingface_hub
+```
+
+---
+
+## 📚 Citation
+
+If you use DinoBloom in your research, please cite:
+
+```bibtex
+@inproceedings{koch2024dinobloom,
+  title={DinoBloom: a foundation model for generalizable cell embeddings in hematology},
+  author={Koch, Valentin and Wagner, Sophia J and Kazeminia, Salome and Sancar, Ece and Hehr, Matthias and Schnabel, Julia A and Peng, Tingying and Marr, Carsten},
+  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
+  pages={520--530},
+  year={2024},
+  organization={Springer}
+}
+```
+
+---
+
+## 📖 Related Work
+
+DinoBloom builds upon:
+- [DINOv2](https://arxiv.org/abs/2304.07193) - Self-supervised vision transformers
+- [Original DinoBloom Paper](https://arxiv.org/abs/2404.05022) - MICCAI 2024
+
+---
+
+## 📄 License
+
+Apache 2.0 - See [LICENSE](LICENSE) file for details.
+
+---
+
+
+For questions or issues, please open an issue on [GitHub](https://github.com/MarrLab/DinoBloom) or contact the authors.

config.json

@@ -0,0 +1,36 @@
+{
+  "model_name": "DinoBloom",
+  "description": "DinoBloom: A foundation model for generalizable cell embeddings in hematology",
+  "variants": {
+    "s": {
+      "architecture": "dinobloom_s",
+      "embed_dim": 384,
+      "num_params": "22M",
+      "checkpoint": "pytorch_model_s.bin"
+    },
+    "b": {
+      "architecture": "dinobloom_b",
+      "embed_dim": 768,
+      "num_params": "86M",
+      "checkpoint": "pytorch_model_b.bin"
+    },
+    "l": {
+      "architecture": "dinobloom_l",
+      "embed_dim": 1024,
+      "num_params": "304M",
+      "checkpoint": "pytorch_model_l.bin"
+    },
+    "g": {
+      "architecture": "dinobloom_g",
+      "embed_dim": 1536,
+      "num_params": "1136M",
+      "checkpoint": "pytorch_model_g.bin"
+    }
+  },
+  "image_size": 224,
+  "mean": [0.485, 0.456, 0.406],
+  "std": [0.229, 0.224, 0.225],
+  "base_model": "DINOv2",
+  "license": "Apache-2.0",
+  "paper": "https://arxiv.org/abs/2404.05022"
+}

pytorch_model_b.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd8e51fd9831858c96cb241a694dd9d64cc28941ec2a923f1fa1e9b5c610a3f
+size 342960457

pytorch_model_g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bff9c85eabb2628e8c741701b6eb23a6ebd61699de85777af99750d6415a39
+size 4539271193

pytorch_model_l.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3963b60942e18e1f66fc77340700f4d408c69ca6d6617c0f94feedbad7caa88f
+size 1213028409

pytorch_model_s.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d40c40ef74867e507783f3d5d341b5d0d65a7efc40b03d526795f07882367d
+size 86574409